Bayesian Sentiment Analytics for Emerging Trends in Unstructured Data Streams

Sahar, Najam and Irshad, Muhammad and Khan, Muhammad (2016) Bayesian Sentiment Analytics for Emerging Trends in Unstructured Data Streams. EAI Endorsed Transactions on Scalable Information Systems, 6 (23): e5. ISSN 2032-9407

[img]
Preview
Text
eai.13-7-2018.159355.pdf - Published Version
Available under License Creative Commons Attribution No Derivatives.

Download (3MB) | Preview

Abstract

Today the computational study of people’s opinion expressed in free form written text is called the field of sentiment analysis and opinion mining. Various research areas such as Natural Language Processing, Data Mining, Text Mining lie in field of Sentiment Analysis and is also becoming major part of importance to organizations because of online commerce is included in their operational strategy. Due to excess of user’s comments, feedback on web there is a need to analyze the user generated text. This research focuses on aspect level sentiment analysis in which identification of aspects and their related sentiments is being done. Opinion analysis helps to identify the polarity of the text and feature extraction. This study is being done to provide an effective and efficient framework to calculate the sentiments of written text by using Naïve Bayes approach. For sentiment analysis dataset of 1060 reviews of different restaurants from online website TripAdvisor.com is being used. The outcome achieved good accuracy 80.833 percent.

Item Type: Article
Uncontrolled Keywords: Naïve Bayes, Bag of Words, Bag of Nouns, Term Frequency, Inverse Document Frequency
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
QA75 Electronic computers. Computer science
Depositing User: EAI Editor II.
Date Deposited: 08 Oct 2020 13:54
Last Modified: 08 Oct 2020 13:54
URI: https://eprints.eudl.eu/id/eprint/701

Actions (login required)

View Item View Item